Introduction to image capturing methodologies, such as sampling of raster images, colour representation and histogram operations. Image processing algorithms for binary images and morphological operations for image segmentation. Theory of linear filters and the application of convolution filters using Fourier transformation. Application of linear low-pass filtering to smoothing and image pyramid computation. Theory of sampling and its relation to local frequency and aliasing effects with application to super/sub-sampling and anti-aliasing. Application of linear high-pass filtering to edge detection, the computation of image gradients and methods for feature extraction based on local gradients.

Introduction to algorithms for extracting local descriptors of feature points, such as scale-invariant feature transformation (SIFT) and SURF. Algorithms for image segmentation based on mathematical representations such as level-sets and Markov-random-fields. Optimisation techniques for solving image segmentation problems. Photometric stereo algorithms for extracting 3d information from single images, such as shape-from-shading. Image sequence analysis using optical flow algorithms. Feature tracking algorithms for image sequences, such as KLT, to facilitate multi-view scene reconstruction and automatic camera calibration.

Theory of statistical parameter estimation. Maximum Likelihood and iterative Least-Squares estimation techniques, such as Gauss-Helmert- and Gauss-Markov-models as well as online estimation methods such as Kalman filters. Robust estimation techniques to cope with outliers in data including robust cost functions and random sampling consensus (RANSAC). Performance analysis techniques like the estimation of empirical parameter accuracy and variance components.

Introduction to the projective geometry of 2d and 3d space. Geometric modelling of the imaging process using linear projective camera models and forward/backward projection of image point and image line features. Estimation of planar homographies and their application to plane-to-plane image mapping, image registration and stitching of panoramic views from multiple images. Epipolar geometry of two and three projective images. Estimation of the fundamental matrix and the trifocal tensor to describe the un-calibrated multi-view geometry. Application of un-calibrated multi-view geometry to projective 3d scene reconstruction from multiple images. Algorithms and techniques for camera calibration. Estimation of the essential matrix to describe calibrated two-view geometry with applications to metric 3d scene reconstruction. Simultaneous localisation and mapping (SLAM) algorithms using bundle adjustment to recover camera and scene geometry from image sequences. Auto-calibration techniques for recovering metric information from video sequences of un-calibrated images.